Results 1 - 10 of 323

Neyman-Pearson Classification, Convexity and Stochastic Constraints

by Xin Tong, Gábor Lugosi - Journal of Machine Learning Research
"... Motivated by problems of anomaly detection, this paper implements the Neyman-Pearson paradigm to deal with asymmetric errors in binary classification with a convex loss ϕ. Given a finite collection of classifiers, we combine them and obtain a new classifier that satisfies simultaneously the two foll ..."
Abstract - Cited by 7 (2 self) - Add to MetaCart
Motivated by problems of anomaly detection, this paper implements the Neyman-Pearson paradigm to deal with asymmetric errors in binary classification with a convex loss ϕ. Given a finite collection of classifiers, we combine them and obtain a new classifier that satisfies simultaneously the two

A Plug-in Approach to Neyman-Pearson Classification

by Xin Tong , Marshall Business School , 2013
"... Abstract The Neyman-Pearson (NP) paradigm in binary classification treats type I and type II errors with different priorities. It seeks classifiers that minimize type II error, subject to a type I error constraint under a user specified level α. In this paper, plug-in classifiers are developed unde ..."
Abstract - Add to MetaCart
Abstract The Neyman-Pearson (NP) paradigm in binary classification treats type I and type II errors with different priorities. It seeks classifiers that minimize type II error, subject to a type I error constraint under a user specified level α. In this paper, plug-in classifiers are developed

Optimal Noise Benefits in Neyman–Pearson and Inequality-Constrained Statistical Signal Detection

by Ashok Patel, Bart Kosko
"... Abstract—We present theorems and an algorithm to find optimal or near-optimal “stochastic resonance ” (SR) noise benefits for Neyman–Pearson hypothesis testing and for more general inequality-constrained signal detection problems. The optimal SR noise distribution is just the randomization of two no ..."
Abstract - Cited by 12 (3 self) - Add to MetaCart
Abstract—We present theorems and an algorithm to find optimal or near-optimal “stochastic resonance ” (SR) noise benefits for Neyman–Pearson hypothesis testing and for more general inequality-constrained signal detection problems. The optimal SR noise distribution is just the randomization of two

Filter design for the detection of compact sources based on the Neyman-Pearson detector

by M. López-caniego, D. Herranz, R. B. Barreiro, J. L. Sanz - Monthly Notices of the Royal Astronomical Society , 2005
"... This paper considers the problem of compact source detection on a Gaussian background. We make a one-dimensional treatment (though a generalization to two or more dimensions is possible). Two relevant aspects of this problem are considered: the design of the detector and the filtering of the data. O ..."
Abstract - Cited by 6 (5 self) - Add to MetaCart
. Our detection scheme is based on local maxima and it takes into account not only the amplitude but also the curvature of the maxima. A Neyman-Pearson test is used to define the region of acceptance, that is given by a sufficient linear detector that is independent on the amplitude distribution

Variations on a theme by Neyman and Pearson

by V. S. Borkar, S. K. Mitter, S. R. Venkatesh , 2004
"... A symmetric version of the Neyman-Pearson test is developed for discriminating between sets of hypotheses and is extended to encompass a new formulation of the problem of parameter estimation based on finite data sets. Such problems can arise in distributed sensing and localization problems in senso ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
A symmetric version of the Neyman-Pearson test is developed for discriminating between sets of hypotheses and is extended to encompass a new formulation of the problem of parameter estimation based on finite data sets. Such problems can arise in distributed sensing and localization problems

On Neyman-Pearson optimisation for multiclass classifiers

by Thomas L, Robert P. W. Duin
"... Typically two procedures are used in optimising clas-sifiers. The first is cost-sensitive optimisation, in which given priors and costs, the optimal classifier weights/thresholds are specified corresponding to min-imum loss, followed by model comparison. This pro-cedure extends naturally to the mult ..."
Abstract - Add to MetaCart
to the multiclass case. The second is Neyman-Pearson optimisation, in which costs may not be certain, and the problem involves specifica-tion of one of the class errors, which subsequently fixes the corresponding error (in the two class case), followed by comparisons between different models. This optimi

Distributed signal detection under the neyman-pearson criterion

by Qing Yan , Senior Member, IEEE Rick S Blum - Information Theory, IEEE Transactions on
"... Abstract-A procedure for finding the Neyman-Pearson optimum distributed sensor detectors for cases with statistically dependent observations is described. This is the first valid procedure we have seen for this case. This procedure is based on a theorem proven in this paper. These results clarify a ..."
Abstract - Cited by 13 (0 self) - Add to MetaCart
Abstract-A procedure for finding the Neyman-Pearson optimum distributed sensor detectors for cases with statistically dependent observations is described. This is the first valid procedure we have seen for this case. This procedure is based on a theorem proven in this paper. These results clarify

Layered Perceptron Versus the Neyman-Pearson Optimal Detection

by Christophe F. Bas, Robert J. Marks N - Proc, IJCNN , 1991
"... A layered perceptron artificial neural network (ANN) is trained to detect positive signals corrupted with noise which, for our test, is Laplacian. Comparison of the ANN performance is made with both Neyman-Pearson optimal and linear detectors. The ANN invariably outperforms the linear detector and i ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
A layered perceptron artificial neural network (ANN) is trained to detect positive signals corrupted with noise which, for our test, is Laplacian. Comparison of the ANN performance is made with both Neyman-Pearson optimal and linear detectors. The ANN invariably outperforms the linear detector

Decentralized detection

by John N. Tsitsiklis - In Advances in Statistical Signal Processing , 1993
"... Consider a set of sensors that receive observations from the environment and transmit finite-valued messages to a fusion center that makes a final decision on one out of M alternative hypotheses. The problem is to provide rules according to which the sensors should decide what to transmit, in order ..."
Abstract - Cited by 177 (8 self) - Add to MetaCart
to optimize a measure of organizational performance. We overview the available theory for the Bayesian formulation, and improve upon the known results for the Neyman-Pearson variant of the problem. We also discuss (i) computational issues, (ii) asymptotic results, (iii) generalizations to more complex

MIMO RADAR DIVERSITY WITH NEYMAN-PEARSON SIGNAL DETECTION IN NON-GAUSSIAN CIRCUMSTANCE WITH NON-ORTHOGONAL WAVEFORMS

by Qian He, Rick S. Blum
"... The diversity gain of a multiple-input multiple-output (MIMO) system adopting the Neyman-Pearson (NP) criterion is derived for a signal-present versus signal-absent scalar hypothesis test statistic and for a vector signal-present versus signal-absent hypothesis testing problem. The results are appli ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
The diversity gain of a multiple-input multiple-output (MIMO) system adopting the Neyman-Pearson (NP) criterion is derived for a signal-present versus signal-absent scalar hypothesis test statistic and for a vector signal-present versus signal-absent hypothesis testing problem. The results
Results 1 - 10 of 323